Add cvector-generator example (#7514)
* add control-vector-generator * calc diff * add comments * proof-of-concept stdlib implementation Implements PCA and file writing using mostly standard libraries. The output is recognized as a functional control vector, but outputs gibberish. * param parsing, refactor, comments Added basic command-line parameters for outfile and one each positive/negative prompt. Refactored some messy code in PCA computation and GGUF exporting. Left a bunch of comments regarding further work needed. * example template completions Implements an example template set built from the positive/negative prompts like the control vector Python implementation. * add multi prompts, multi-thread for PCA * fix mem error * add debugs * fix matrix transpose multiplication you have got to be kidding me * preliminary template/multiprompt support model is running out of context and that ought to be fixed (segfaulting) but other than that it looks goodish * fix zero output & param parsing, functional templating fixed a bug where the output file had no tensor data/was all zero fixed a bug where single hyphen flags were not being correctly parsed implements creation of templated prompts from input (still need to adapt based on model) * fix square_diff matmul index range and CRLF->LF line endings fixed a logic error where square_diff would not multiply all rows fixed a formatting error where the provided completions.txt had CRLF line endings * add command-line args for num threads, num completions file lines, always reload model refactored a few things and did what the commit message says on the tin * code aestheticization * fix compiler warnings * in-series multithreading for prompt embedding? added commented-out code to attempt to start implementing mutlithreading for embedding in main * remove unnecessary multithreading * interim fix memory leak * translated everything but PCA (I think) * tentatively translate the rest * fix ggml errors and make new ones at least it compiles and runs * fix cb_eval * temporary commit while I move dev environments it finally outputs a functioning control vector - "functioning" in the sense that it can be loaded and it clearly has the right idea, but makes the model incoherent * update debug statements * pre-tokenize so we can allocate correct memory to ctx_diffs_wrapped * update comments * (wip) refactor * clean up PCA ggml implementation * fix shape of v_diff_original * add n_batch for pca * working version * remember to copy back the last_eigenvector * fix n_completions * bring back n_completions * default n_pca_batch to 20 * fix macos build * add to makefile all targets * use ggml_format_name * add readme * fix .editorconfig * use ggml_backend_tensor_copy * attemp to fix compile problem on mac * fix compile warn * reuse allocr * move param parser to common * better error handling * clean up a bit * add print_usage * shorten help msg * beautify help msg * escape prompt by default * change compile target to llama-cvector-generator * typo * disable GPU for PCA * code style --------- Co-authored-by: Christian Zhou-Zheng <christianzhouzheng@gmail.com>
This commit is contained in:
Xuan Son Nguyen
GitHub
parent
7b2f4a7d19
commit
0c7b3595b9
12 changed files with 1522 additions and 0 deletions
|
|
@ -1576,6 +1576,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
|||
return true;
|
||||
}
|
||||
params.out_file = argv[i];
|
||||
params.cvector_outfile = argv[i];
|
||||
return true;
|
||||
}
|
||||
if (arg == "-ofreq" || arg == "--output-frequency") {
|
||||
|
|
@ -1610,6 +1611,55 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
|||
params.i_chunk = std::stoi(argv[i]);
|
||||
return true;
|
||||
}
|
||||
// cvector params
|
||||
if (arg == "--completions-file") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.cvector_completions_file = argv[i];
|
||||
return true;
|
||||
}
|
||||
if (arg == "--positive-file") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.cvector_positive_file = argv[i];
|
||||
return true;
|
||||
}
|
||||
if (arg == "--negative-file") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.cvector_negative_file = argv[i];
|
||||
return true;
|
||||
}
|
||||
if (arg == "--completions") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.n_completions = std::stoi(argv[i]);
|
||||
return true;
|
||||
}
|
||||
if (arg == "--pca-batch") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.n_pca_batch = std::stoi(argv[i]);
|
||||
return true;
|
||||
}
|
||||
if (arg == "--pca-iter") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
return true;
|
||||
}
|
||||
params.n_pca_iterations = std::stoi(argv[i]);
|
||||
return true;
|
||||
}
|
||||
#ifndef LOG_DISABLE_LOGS
|
||||
// Parse args for logging parameters
|
||||
if (log_param_single_parse(argv[i])) {
|
||||
|
|
@ -1931,6 +1981,16 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
|
|||
options.push_back({ "logging", " --log-append", "Don't truncate the old log file." });
|
||||
#endif // LOG_DISABLE_LOGS
|
||||
|
||||
options.push_back({ "cvector" });
|
||||
options.push_back({ "cvector", "-o, --output FNAME", "output file (default: '%s')", params.cvector_outfile.c_str() });
|
||||
options.push_back({ "cvector", " --positive-file FNAME", "positive prompts file, one prompt per line (default: '%s')", params.cvector_positive_file.c_str() });
|
||||
options.push_back({ "cvector", " --negative-file FNAME", "negative prompts file, one prompt per line (default: '%s')", params.cvector_negative_file.c_str() });
|
||||
options.push_back({ "cvector", " --completions-file FNAME",
|
||||
"completions file (default: '%s')", params.cvector_completions_file.c_str() });
|
||||
options.push_back({ "cvector", " --completions N", "number of lines of completions file to use (default: %d)", params.n_completions });
|
||||
options.push_back({ "cvector", " --batch-pca N", "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch });
|
||||
options.push_back({ "cvector", " --iter-pca N", "number of iterations used for PCA (default: %d)", params.n_pca_iterations });
|
||||
|
||||
printf("usage: %s [options]\n", argv[0]);
|
||||
|
||||
for (const auto & o : options) {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue